Dear Mahout Team,

I am a student new to machine learning and i am trying to build a
recommender using mahout.

My dataset is a csv file as an input but it has many fields as text and i
understand mahout needs numeric values.
First of all i would like your input as to what kind of recommender would
best fit my dataset(I have considered many approaches such as neighbourhood
methods,latency models etc) but i still am not sure what is best for my
recommender.

I looked up spark row similarity but i am not sure if it will suit my needs
as i want to build my recommender as a java application with an interface.

Secondly please explain how to calculate preference strength and do i need
it.

I have mainly implicit data about customer transaction history.

The fields are as follows:

customer id - numeric
product id - text
postal code - text
sales - numeric
product category - text
shipping code - text
potential growth - text
territory - text
Online Customer - Boolean


Potential growth here suggests the strength what kind of future business
can be build with a particular customer.(A is highest,E is lowest)

Kindly contact me with your ideas and suggestions.




Best Regards,
Yash Patel

Reply via email to